End of training

README.md

@@ -1,11 +1,24 @@
 ---
 base_model: HuggingFaceTB/135M-lc-100k-rope-12B
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceTB/magpie-ultra-v1.0-top-300K-short-H4
+- HuggingFaceTB/OpenHermes-2.5-H4-200k
+- HuggingFaceTB/ifeval-like-data-36k-H4
+- HuggingFaceTB/everyday-conversations-llama3.1-2k
+- HuggingFaceTB/self-oss-instruct-sc2-H4
+- HuggingFaceTB/summarization-data-10k-H4
+- HuggingFaceTB/smollm-v2-summarization
+- HuggingFaceTB/smollm-v2-rewriting-50k-H4
+- HuggingFaceTB/explore-instruct-rewrite-H4
+- HuggingFaceTB/LongAlign-16k-ctx-english-H4
 model-index:
 - name: smollm2-135M-8k-lc100k-mix1-ep2
   results: []
@@ -17,7 +30,7 @@ should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/loubnabnl/huggingface/runs/bxdnlpsh)
 # smollm2-135M-8k-lc100k-mix1-ep2
 
-This model is a fine-tuned version of [HuggingFaceTB/135M-lc-100k-rope-12B](https://huggingface.co/HuggingFaceTB/135M-lc-100k-rope-12B) on the generator dataset.
+This model is a fine-tuned version of [HuggingFaceTB/135M-lc-100k-rope-12B](https://huggingface.co/HuggingFaceTB/135M-lc-100k-rope-12B) on the HuggingFaceTB/magpie-ultra-v1.0-top-300K-short-H4, the HuggingFaceTB/OpenHermes-2.5-H4-200k, the HuggingFaceTB/ifeval-like-data-36k-H4, the HuggingFaceTB/everyday-conversations-llama3.1-2k, the HuggingFaceTB/self-oss-instruct-sc2-H4, the HuggingFaceTB/summarization-data-10k-H4, the HuggingFaceTB/smollm-v2-summarization, the HuggingFaceTB/smollm-v2-rewriting-50k-H4, the HuggingFaceTB/explore-instruct-rewrite-H4 and the HuggingFaceTB/LongAlign-16k-ctx-english-H4 datasets.
 It achieves the following results on the evaluation set:
 - Loss: 1.8390
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.0,
+    "eval_loss": 1.8389793634414673,
+    "eval_runtime": 84.0638,
+    "eval_samples": 190563,
+    "eval_samples_per_second": 154.609,
+    "eval_steps_per_second": 4.842,
     "total_flos": 173253108695040.0,
     "train_loss": 1.2838877389321521,
     "train_runtime": 2377.8575,

config.json

@@ -27,6 +27,6 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.42.3",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 49152
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 1.8389793634414673,
+    "eval_runtime": 84.0638,
+    "eval_samples": 190563,
+    "eval_samples_per_second": 154.609,
+    "eval_steps_per_second": 4.842
+}

runs/Oct31_07-14-36_ip-26-0-170-143/events.out.tfevents.1730361415.ip-26-0-170-143.2039241.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f54b2e93d1bc23b56be24a10cf2df5ebb09f4bcc45e186fc273ca1c0884b931a
+size 359